Solar-Decision-JEV-27B-GGUF

GGUF ladder for the r32 + solar merge (the bf16 repo SargeDev/Solar-Decision-JEV-27B). MTP/nextn drafter tensors are preserved in the f16 export (blk.64.nextn.*) so speculative decoding works in llama.cpp.

Sizes

Q4_K_M is the daily-driver pick; Q6_K for maximum fidelity; Q5_K_M in between.

The full ladder

Every size below is in this repo, all built from the same f16 export and verified (866 tensors each, MTP/nextn drafter tensors preserved so speculative decoding works in llama.cpp). The benchmark numbers are measured on one GB10 (GB10-class), CUDA build, -ngl 99, pp512 / tg128, 3 repetitions.

The honest headline for this ladder

The decision-gate numbers for the combined merge are on the bf16 card. This ladder is the same weights in GGUF form. The measured decision-gate accuracy of the combined merge is below its r32 parent (choice top-1 0.8162 vs 0.8693) — see the bf16 card for the full ablation. We are publishing the ladder because it is the artifact people actually run, with the numbers attached.

Quick start

llama-server -m Jev_Qwen3.8-27B-Judgment-Combined-Q4_K_M.gguf -ngl 99 --jinja \
  --chat-template-kwargs '{"enable_thinking": false}'

Decision gate (AutoTrust-style, test_set_30k with yuri_v1 D1 placeholders excluded)

Read this table carefully, because it contains two very different comparisons.

• The sibling merge is our other build, scored on the same 27,695 rows with the same harness and the same head + calibration. It is a sibling model, not a quality bar — but it is the honest apples-to-apples reference for what the lm_head LoRA is worth.
• AutoTrust reference is the number published by the authors of the original AutoTrust work for their model on this task set. This is the bar.

On the typed-decision kinds (multiple-choice choice, ordinal score) this model is still below the published AutoTrust reference, and the gap is large - not a rounding difference. On the binary noul kind the gap is narrower. Cells marked "(below bar)" differ from the published reference by more than 5 points.

What this means: the fine-tune produces a usable decision instrument and a clearly better everyday-chat model than its base (see the benchmark matrix below), but it is not a reproduction of AutoTrust-level typed-decision accuracy. Treat the choice and score columns as an open result, not a solved one. We are publishing the numbers as measured, including the gap.

Harness validation. These numbers were produced by our own HTTP gate client, so we checked it against a known path: re-gating the r32 merge reproduced the reference's own numbers to within 0.001 on every metric (choice top-1 0.8704 -> 0.8693, score KL 0.0623 -> 0.0619, noul AUROC 0.9920 -> 0.9919). The harness is sound, so the gaps above are real.

Ablation: where the decision readout has to live

All four rows below are scored on the SAME 27,695 rows, with the SAME harness and the SAME decision head + calibration. The only difference is where the decision distribution is produced.

Two findings, in order of how much they matter:

1. The readout has to be trained INTO the model. A separate projection over the final hidden state (the solar r16 row) reaches only 0.5054 choice top-1; the same backbone with an lm_head LoRA in the training loop reaches 0.8693 on the identical rows. A separate projection can work, but it needs the backbone to cooperate, and a backbone trained without the readout in the loop does not.

2. Adding a second, readout-free adapter on top makes the typed-decision accuracy WORSE, not better. The combined row is the r32 merge plus the solar r16 delta applied on top (bit-exact arithmetic, verified). It lands between the two parents on every metric - 0.8162 choice top-1, between r32's 0.8693 and solar's 0.5054 - rather than above r32. The two LoRA deltas are near-orthogonal (mean cosine 0.003), so they do not cancel, but solar's delta still degrades the readout r32 trained.

We publish the combined row because it is a real, reproducible result, but the r32+lm_head merge is the better model and is the one this release recommends. We are not going to present a merge as an improvement when our own numbers say it is a regression.

Benchmark matrix (lm-eval-harness 0.4.13, greedy, same prompts for every row)

Questions scored per task:

Note: GSM8K scored with flexible-extract (the model answers in its own format). MMLU subset subjects: high_school_mathematics, college_biology, professional_psychology, jurisprudence, machine_learning, astronomy, global_facts, logical_fallacies (5-shot, _generative variants). MMLU --limit applies PER SUBJECT, so the subset is 8 x per-subject-limit questions.

Reproducibility: decoding is greedy (do_sample=False, temperature 0, seed 1234), but the server batches concurrent requests, and batch composition changes floating-point reduction order. Repeat runs of the same config can therefore differ by a point or two on the small-n tasks. The error bars in the table are the harness's own stderr over the scored rows.

Lineage & credits

This release is a descendant of the earlier SargeDev/JEV-27B-Uncensored and SargeDev/JEV-27B-VL-Uncensored repos. The credit chain is unchanged and is reproduced here in full:

• AutoTrust AI — Blocks-of-Experts recipe, the System-1 decision LoRA (r16/r32) + 24-slot decision head, and the serve_decide.py decision harness, from autotrust/JEV-27B and autotrust/JEV-27B-VL (Apache-2.0). The r32 adapter used here is theirs, unmodified: the backbone LoRA with the decision head re-expressed as an lm_head LoRA, so only the 24 verbalizer rows of the output projection change.
• huihui-ai — the abliterated (uncensored) Qwen3.8-27B backbone used here (Huihui-Qwen3.8-27B-abliterated, Apache-2.0; layers 18-51 ablated, vision tower untouched).
• SargeDev — jev-distill-corpus-v3, the 740,957-row calibrated typed-decision corpus AutoTrust's JEV models were trained on (Apache-2.0), and the solar r16 adapter trained here on solar-decisions-corpus-v4 (the 1,219-step JEV System-1 run, 17-domain tokenized mix).
• Qwen — Qwen3.8-27B base (Apache-2.0).
• TypeSafe AI — Jev 1.13, the original closed teacher behind the System-1 typed-decisions framing (referenced; not redistributed).

Base: huihui-ai/Qwen3.8-27B-abliterated (bf16; the text-only builds strip the vision tower and serve as a plain qwen3_5_text causal LM, the VL build keeps the tower and serves as qwen3_5 / Qwen3_5ForConditionalGeneration).

• Adapters — this release ships two, and they are NOT interchangeable:
  • solar r16 (alpha 32, 400 modules, no lm_head): trained 1,219 steps on the JEV System-1 corpus (solar-decisions-corpus-v4 tokenized mix: T1 gold domains + memory_relevance + 17-domain fill), KL+RPS decision-head distillation objective (AutoTrust-style), cosine LR 2e-4, KL_W 1.0, RPS_W 0.3. Merged with peft merge_and_unload; merge fidelity verified by re-gating the bare merged model (it reproduced the adapter-mounted numbers).
  • r32 (alpha 64, 401 modules, includes lm_head): the backbone LoRA plus the 24-slot decision head re-expressed as an lm_head LoRA (only the 24 verbalizer rows change), so a typed decision is a single prefill step with max_tokens=1 constrained to the option tokens.
• Decision head + calibration.json (shipped in this repo root): the instrument-panel piece agents call for numeric confidence — the 24-slot verbalizer id list, the per-slot bias, and the per-kind temperature. This is the SAME head and the SAME calibration file (verified byte-identical, md5 11359173… and 7f0f3914…) that produced every gate number in this card, so a consumer reproducing our numbers reproduces them exactly. For everyday natural-language judgment, chat with the model directly and set enable_thinking:false in chat_template_kwargs.
• Everything measured on one NVIDIA GB10 (DGX Spark-class); quantized with llmcompressor 0.14.0 (NVFP4) and llama.cpp (GGUF ladder).